Arbr Docs
← Home Star on GitHub
Providers & models  ·  menu

Core

Providers & models

Eight providers are built in, plus any OpenAI-compatible endpoint, including a LiteLLM proxy. Connect a key once and its models become routable. Arbr never hands provider credentials to client applications.

Built-in providers

ProviderIDEnv varDefault model
AnthropicanthropicANTHROPIC_API_KEYclaude-haiku-4-5
OpenAIopenaiOPENAI_API_KEYgpt-4o-mini
Google GeminigeminiGEMINI_API_KEYgemini-2.5-flash
Amazon Bedrockbedrock-novaAWS_ACCESS_KEY_ID + secretus.amazon.nova-lite-v1:0
DeepSeekdeepseekDEEPSEEK_API_KEYdeepseek-chat
Moonshot AImoonshotMOONSHOT_API_KEYmoonshot-v1-8k
xAI (Grok)xaiXAI_API_KEYgrok-3-mini
GroqgroqGROQ_API_KEYllama-3.3-70b-versatile

Connecting a provider

Two ways, and you can mix them:

Demo mode

With zero provider keys configured, Arbr runs in demo mode: every dashboard, the recommendation engine, and the routing controls work on seeded data. Only live /v1 calls are disabled until you add a key.

LiteLLM & custom OpenAI-compatible providers

Arbr sits in front of LiteLLM. It's an upstream Arbr connects to, not a replacement. You keep LiteLLM's provider breadth and layer Arbr's routing, evidence, budgets, and governance on top. Connect it from the dashboard (Discover → Import models), or point the openai provider at any OpenAI-compatible base URL:

env
OPENAI_BASE_URL=https://your-litellm-host/v1
OPENAI_API_KEY=sk-litellm-...

The same mechanism connects vLLM, Ollama, NVIDIA NIM, or any other OpenAI-compatible server. Requests, tool calls, and streaming pass through the full chain unchanged.

The model registry

Arbr ships 29 built-in models with pricing, tier, and capability metadata. The registry drives cost tracking, recommendations, guardrail downgrades, and routing. A model without a pricing entry still works as a pass-through. Its cost is logged as $0 and left out of savings claims until you add pricing.

A sample of the registry

ModelProviderTier$ / 1M in → out
claude-opus-4-8anthropicpremium$5 → $25
claude-sonnet-4-6anthropicmid$3 → $15
claude-haiku-4-5anthropiclight$1 → $5
gpt-4oopenaipremium$2.50 → $10
gpt-4o-miniopenailight$0.15 → $0.60
gemini-2.5-progeminipremium$1.25 → $10
gemini-2.5-flashgeminilight$0.30 → $2.50
nova-lite-v1:0bedrock-novalight$0.06 → $0.24
deepseek-chatdeepseeklight$0.27 → $1.10
grok-3-minixailight$0.30 → $0.50
llama-3.3-70b-versatilegroqmid$0.59 → $0.79

Add or edit models from the dashboard, the admin API, or the seed. Built-in pricing updates on re-seed without touching your custom entries.

Tool-call support

Not every provider supports function calling through Arbr today. GET /v1/models returns a toolCallSupported flag per model, so a client knows whether to enable its function-calling UI. It's true for OpenAI, DeepSeek, Groq, xAI, Moonshot, LiteLLM, and Amazon Nova. It's false for Gemini, Anthropic, and non-Nova Bedrock models. If your agent needs tools, pin a tool-capable model rather than using auto.

Per-provider notes

Provider-specific quirks, like Opus rejecting temperature, Gemini's thinking-variant JSON, and Bedrock IAM permissions, are documented per provider in the providers reference on GitHub ↗.